AI 太喜欢写空话/废话了,最近我和 @hejiyan 收集了一些例子并分析其中的具体问题,整理了一份关于何为空话/废话的文档,可以直接发给 AI: https://nofluff.0x01.me/
👍12

Channel
@SmartHypercube_channel
On this record: Growth · Engagement · What this channel posts · Reactions · Stars · Posts · Citations · Cite this entry
275subscribers
+0 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1001417867063 |
|---|---|
| Type | Channel |
| Username | @SmartHypercube_channel |
| Description | @SmartHypercube 随便发最近关注的东西 欢迎找我私聊讨论 可以使用 Telegram 的转发功能转发消息 |
| Created | Between 1 April 2019 and 31 August 2021— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 8 August 2026 |
| Last confirmed live | 8 August 2026 |
| Measurements held | 2 |
| On Telegram | t.me/SmartHypercube_channel |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 8 Aug 2026, 08:45 | 275 | no change |
| 7 Aug 2026, 23:35 | 275 | first reading |
20 posts held, back to 27 March 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 20 posts for this entry, the most recent from 9 July 2026. An engagement rate over an empty window would be a number about nothing.
Lifetime counters from Telegram’s own channel header, read 8 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
75 reactions across 14 posts, in 1 kind.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 75 | 100.0% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 14 of the 20 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 75reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 20 most recent posts we hold, published 27 March 2026 to 9 July 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @SmartHypercube_channel. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.
Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.
This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.
Counted over the 20 most recent posts we hold for this entry, published 27 March 2026 to 9 July 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.
AI 太喜欢写空话/废话了,最近我和 @hejiyan 收集了一些例子并分析其中的具体问题,整理了一份关于何为空话/废话的文档,可以直接发给 AI: https://nofluff.0x01.me/
👍12
^ 这几年我越来越意识到了这一点,并且发现我的计算机领域背景在一定程度上阻止了我更早意识到现实其实是这样的。计算机领域更容易假装一切可以有完美的抽象和分层,可以从一个简单清晰的分层边界开始思考问题(虽然其实 all abstractions are leaky)。其他领域中无法漂亮地分层、以至于必须处理巨量的细节的情况简直太多了,我感到我看待世界和任何问题的方式都发生了变化。
👍10
现实拥有惊人数量的细节 (2017) 原文:https://johnsalvatier.org/blog/2017/reality-has-a-surprising-amount-of-detail 阅读时间:8 分钟 分数:187
https://en.wikipedia.org/wiki/Two_Generals%27_Problem
很多年前我和 @zzh1996 讨论过的一个问题,我觉得它的证明很好理解并且结论在很多问题上有启发性: 甲乙二人通过一个可能丢包的网络通信,甲可以随时给乙发消息,乙也可以随时给甲发消息,每条消息分别有可能被对方收到或者丢了。他们希望找到一个方法协商要不要出门一起吃饭,也就是说,每个人都执行一个算法,收发一些消息后决定自己要不要出门。希望找到满足以下性质的算法: 1. 无论网络如何丢包,只允许两种结果,要么两人都出门了,要么两人都没出门 2. 如果网络完全没丢包,最终结果必须是两人都出门了 3. 如果网络完全丢包,最终结果必须是两人都没出门 (后两条性质的目的是禁止把算法设计成“什么消息都不用发,直接出门”或者“直接不出门”) 这样的算法是不存在的,证明: 如果网络完全没丢包,因为性质 2,最终甲乙都会出门。又因为性质 3,甲乙都出门的话一定是发送过至少一条消息的。我们把网络中最后一条消息称为消息 X,不妨设 X 是甲发给乙的…
👍7
https://modelware.zgci.ac.cn/blog/2026/toolize/ (软件智能研究所持续招人中,尤其想找对软件/AI感兴趣、能独立钻研新事物的工程师/研究员,详情见 https://modelware.zgci.ac.cn/jobs/ ,也可以直接联系我~)
👍7
Posted without readable text
Codex 有个机制,当 Quota 用尽时,它依然允许跑完最后一轮对话。 利用这一点,只要在配置里开启 [features] default_mode_request_user_input = true 并用 Prompt 诱导它不断调用该工具,就能把对话卡在同一个 turn_id 里无限套娃续航😂 因为调用工具并不算新的一轮对话,但 request_user_input 工具实质上提供了插入新 prompt 的能力 附送提示词: 总是在结束前调用 request_user_input 工具告知用户当前进展,接收用户的反馈。
👍6
吐槽一句,arXiv 的 API 真是烂透了,维护 paper.dou.ac 的过程中遇到过各种奇奇怪怪的问题,最近一段时间尤其更糟了,已经发布的论文 PDF 文件大小为 0 和 query API 查不到这两个问题发生频率在增加,例如: PDF 文件大小为 0: abs: https://arxiv.org/abs/2605.23998v1 有问题的 pdf: https://arxiv.org/pdf/2605.23998v1 query API 查不到: abs: https://arxiv.org/abs/2605.27010v1 有问题的 API: https://export.arxiv.org/api/query?id_list=2605.27010v1 (一般来说有这样问题的论文会在发布后一到几天内悄悄被修好,所以过几天再检查上面举的例子可能就没问题了)
👍1
https://modelware.zgci.ac.cn/blog/2026/zgent-design-journey-3/
👍5
https://yun.0x01.me/ 我之前就想玩一玩把相同的韵母和声调用在每一句,但不追求遵守格律。今天终于让 AI 帮我写了个小工具,顺便统计了一下常用字的韵母分布频率。 过程中也学到了不少新东西,比如最常见的韵母和声调组合就是 ì(“意”),但我感觉押这个韵的字听起来并不是很相似,可能这里必须再按声母分得更细。 以及有一个叫“十三辙”的概念我以前一直不知道,用它同时搜索多种介韵母+韵母的组合比较有效。好了我担心我再说怪话有的朋友就要暴跳,赶紧凑足四句就跑掉(笑)。
👍6
Photo, posted without a caption
Showing the 12 most recent of 20 posts we hold for @SmartHypercube_channel. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Citation-graph rank — 489,595 of 1,169,250entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Republishes
Channels on the register whose posts this channel has forwarded.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 8 August 2026 — this entry's latest reading, not the date you are reading this.
“Hypercube's Channel” (@SmartHypercube_channel), 275 subscribers as measured 8 August 2026. Telegram Register, tgregister.com/channel/SmartHypercube_channel.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.